Update model card and embedded training curves

README.md

@@ -14,7 +14,7 @@ tags:
 
 ## Summary
 
-This repo contains the merged chat model for the combined with metadata branch of the metadata localization project. It was produced by supervised fine-tuning on the project QA benchmark after continued pretraining.
+This repo contains the merged chat model for the combined with metadata branch of the metadata localization project. It was produced by supervised fine-tuning on the project QA benchmark after project pretraining.
 
 ## Variant Metadata
 
@@ -58,6 +58,22 @@ This repo contains the merged chat model for the combined with metadata branch o
 - `per_device_train_batch_size=2`, `gradient_accumulation_steps=8`
 - LoRA targets: `q_proj`, `k_proj`, `v_proj`, `o_proj`, `gate_proj`, `up_proj`, `down_proj`
 
+## Training Curves
+
+Static plots below were exported from the private Weights & Biases run and embedded here for public access.
+
+### Train Loss
+
+![Train Loss](assets/train_loss.png)
+
+### Learning Rate
+
+![Learning Rate](assets/learning_rate.png)
+
+### Gradient Norm
+
+![Gradient Norm](assets/grad_norm.png)
+
 ## Project Context
 
 This model is part of the metadata localization release. Related checkpoints and variants are grouped in the public Hugging Face collection [Metadata Conditioned LLMs](https://huggingface.co/collections/iamshnoo/metadata-conditioned-llms).
@@ -65,4 +81,4 @@ This model is part of the metadata localization release. Related checkpoints and
 - Project repository: [https://github.com/iamshnoo/metadata_localization](https://github.com/iamshnoo/metadata_localization)
 - Paper: [https://arxiv.org/abs/2601.15236](https://arxiv.org/abs/2601.15236)
 
-Last synced: `2026-04-02 13:51:17 UTC`
+Last synced: `2026-04-02 14:48:16 UTC`